Optimum Cost and Eco-Friendly Power Management in a Micro-Grid, Based on Multi-Agent Reinforcement Learning
Bibliographic record
Abstract
This paper suggests adopting reinforcement learning-based (RL) strategy to overcome obstacles to micro-grid (MG) power management. Intended MG includes battery energy storage system (BESS), wind turbine (WT), photovoltaics (PV), and combined cooling, heating, and power (CCHP) related units. In order to achieve a reliable and eco-friendly MG, a model-free RL approach is applied to preserve the multi-objective fuel and CO2 emission price function as minimal as conceivable. Moreover, inclusion of a penalty factor in the cost function acknowledges the inherent variability of WT and PV systems. As such, it is essential to account for the potential risks and costs associated with their intermittent power generation. Therefore, a multi-agent reinforcement learning (MARL) solution is put forward to handle the task. By merging smaller tasks each individual agent undertakes, MARL aim to solve the challenging problem of identifying the optimal operating power points amongst generation units, rather than just one agent. Moreover, to empower the proposed strategy, grid search is employed to tune the hyperparameters, as a systematic technique involves extensively exploring predefined range of hyperparameter values. The outcomes reveal the suggested MARL adequately allocates the power generation to the micro-turbine in CCHP system, sources of renewable energy, as well as the BESS.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".